Reducing Discrimination in Learning Algorithms for Social Good in Sociotechnical Systems
Sociotechnical systems within cities are now equipped with machine learning algorithms in hopes to increase efficiency and functionality by modeling and predicting trends. Machine learning algorithms have been applied in these domains to address challenges such as balancing the distribution of bikes throughout a city and identifying demand hotspots for ride sharing drivers. However, these algorithms applied to challenges in sociotechnical systems have exacerbated social inequalities due to previous bias in data sets or the lack of data from marginalized communities. In this paper, I will address how smart mobility initiatives in cities use machine learning algorithms to address challenges. I will also address how these algorithms unintentionally discriminate against features such as socioeconomic status to motivate the importance of algorithmic fairness. Using the bike sharing program in Pittsburgh, PA, I will present a position on how discrimination can be eliminated from the pipeline using Bayesian Optimization.
Claim Mapping Visualization and Analysis: COVID-19 Twitter Data
My summer 2020 internship was with IQT Labs where I was advised by Dr. Nina Lopatina. My project was focused on the Infodemic: the misinformation about COVID-19 that is overwhelming social media platforms. The goal of the project was to enable “information epidemiology” by making a spatial-temporal visualization of the life cycle of COVID-19 claims and narratives on Twitter. The open source visualization tool I created maps tweets about COVID-19 misinformation to identify when and where a claim or narrative started as well as when it became associated with a left/right bias.
Using Object Tracking Techniques to Non-Invasively Measure Thoracic Rotation Range of Motion
Accurately calculating the flexibility of a patient undergoing physical therapy is a difficult task and results in inconsistent measurements. Flexibility and ability to do certain tasks are parameters used to determine the patient's progress in therapy and training. To achieve a consistent and accurate reading on ones’ flexibility, specifically for a patient's torso, computer vision techniques have been combined with hardware to create a user-friendly application and product for the patients and physical therapists to interact with. This work was presented in October 2020 at ACM ICMI 2020 Face and Gesture Analysis for Health Informatics Workshop. See News section to read the paper!
Adults' Perspective on Public Bike Sharing System in Manizales, Colombia
This research project will be conducted in Manizales, Colombia in May 2021 (due to Coronavirus travel restrictions). This study is to better understand which factors influence how adults in Manizales, Colombia assess and evaluate the public bike sharing system Manizales En Bici.